Perception Learning, Prediction and Motion Planning for Energy Efficient Driving of Connected and Automated Vehicles

Perception Learning, Prediction and Motion Planning for Energy Efficient Driving of Connected and Automated Vehicles

Transportation-related fuel consumption and greenhouse gas emissions have received increasing public and concern in recent years. With the advent of Connected Vehicle (CV) Technology, a number of advanced Eco-driving technologies have been developed to guide vehicles driving in an eco-friendly way. In both urban arterial and highway networks, vehicles and road infrastructure can communicate and interact with each other as individual intelligent agent, which can significantly improve the overall traffic performance in terms of safety, mobility and environmental sustainability. To reduce energy consumption and mitigate the environmental impact of transportation activities in the real world, in this dissertation, the researcher will propose a variety of agent-based intelligent technologies based on spatial and temporal data crowd sourcing, machine learning and advanced control algorithm in the connected vehicle environment. 

More specifically, they applied artificial intelligent for forecasting traffic condition, abnormality, queue dynamic state and integrating with advanced lateral control and eco-driving algorithm in both urban arterial and highways. There are three major tasks in the project: 

  1. Prediction-based Eco-Approach and Departure at Signalized Intersections 
  2. A Co-optimization of Connected Hybrid Electric Bus Transit Strategy and Vehicle Powertrain-Dynamics in Urban Corridors 
  3. Traffic Abnormality Prediction Application for Connected Automated Vehicles (CAVs) in a Mixed Traffic Environment

Publications

Research Area

Tags